{"data":{"slug":"ai-hypercomputer-jetstream","name":"JetStream","tagline":"JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).","github_url":"https://github.com/AI-Hypercomputer/JetStream","owner":"AI-Hypercomputer","repo":"JetStream","owner_avatar_url":"https://avatars.githubusercontent.com/u/181000646?v=4","primary_language":"Python","stars":451,"forks":66,"topics":["gemma","gpt","gpu","inference","jax","large-language-models","llama","llama2","llm","llm-inference","llmops","mlops","model-serving","pytorch","tpu","transformer"],"archived":false,"github_pushed_at":"2026-01-05T17:51:16+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/ai-hypercomputer-jetstream","markdown_url":"https://www.graphcanon.com/tools/ai-hypercomputer-jetstream.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ai-hypercomputer-jetstream","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ai-hypercomputer-jetstream","description":"JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).","homepage_url":null,"license":"Apache-2.0","open_issues":25,"watchers":22,"ai_summary":null,"readme_excerpt":null,"github_created_at":"2024-03-01T00:24:07+00:00","created_at":"2026-07-11T11:46:14.173791+00:00","updated_at":"2026-07-11T11:46:16.293307+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"llama","name":"llama"},{"slug":"gemma","name":"gemma"},{"slug":"gpu","name":"gpu"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"gpt","name":"gpt"},{"slug":"inference","name":"inference"},{"slug":"llama2","name":"llama2"},{"slug":"jax","name":"jax"}],"trust":{"provenance":{"is_fork":false,"github_id":765455287,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T11:46:14.805Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":null,"days_since_push":186,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:46:15.327Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T11:46:15.114Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T11:46:15.114Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-07-11T11:46:15.114Z"}}}}